Title :
Improvements in HMM-based isolated word recognition system
Author :
Peinado, A.M. ; Lopez, J.M. ; Sanchez, V.E. ; Segura, J.C. ; Ayuso, A. J Rubio
Author_Institution :
Dept. de Electro. y Tecnologia de Computadores, Granada Univ., Spain
fDate :
6/1/1991 12:00:00 AM
Abstract :
A speaker-independent isolated word recognition system for voice-activated robots is introduced. Since such an application requires a fast and accurate recognition system, discrete hidden Markov models and vector quantisation techniques have been used. Different initialisations for VQ and HMM training are tested to obtain improvements over the other systems. The final models can be evaluated using a temporal normalisation of the HMM scores. A threshold-based rejector can also be established using this temporal normalisation.<>
Keywords :
Markov processes; data compression; encoding; speech recognition; HMM scores; HMM-based isolated word recognition system; discrete hidden Markov models; speaker-independent system; temporal normalisation; threshold-based rejector; training algorithms; vector quantisation; voice-activated robots;
Journal_Title :
Communications, Speech and Vision, IEE Proceedings I
